Triple

T4048035
Position Surface form Disambiguated ID Type / Status
Subject Graham family E84114 entity
Predicate businessInterest P3849 FINISHED
Object Kaplan, Inc. E385830 NE FINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Kaplan, Inc. | Statement: [Graham family, businessInterest, Kaplan, Inc.]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kaplan, Inc.
Context triple: [Graham family, businessInterest, Kaplan, Inc.]
  • A. Kaplan, Inc. chosen
    Kaplan, Inc. is a global educational services company best known for its test preparation, professional training, and higher education programs.
  • B. Kaplan
    Kaplan is a surname most notably associated with Mordecai Kaplan, an influential 20th-century rabbi and theologian who founded Reconstructionist Judaism.
  • C. Kaplan University
    Kaplan University was a former U.S.-based for-profit online and campus-based higher education institution offering associate, bachelor’s, and graduate degree programs to working adults.
  • D. Capco
    Capco is a global management and technology consultancy specializing in the financial services industry.
  • E. Shorenstein Company
    Shorenstein Company is a prominent privately held real estate investment and development firm based in San Francisco, known for owning and managing major commercial office properties across the United States.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69aed930bd5c819083e7dcc14fc44f69 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aefb81040481909b22e4c445ecae0f completed March 9, 2026, 4:55 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5565466648190802a9b8fd88c3572 completed March 14, 2026, 12:36 p.m.
Created at: March 9, 2026, 3:37 p.m.